© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 63290
    Prev
    Next
    INDEX
    Explanations

    negations or phrases indicating absences or lack

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    nze
    -0.06
    roupon
    -0.06
    yp
    -0.06
    roulette
    -0.06
    rella
    -0.06
    igi
    -0.06
    εί
    -0.06
    741
    -0.06
    itage
    -0.06
    abee
    -0.06
    POSITIVE LOGITS
     wonder
    0.08
     lie
    0.07
     matter
    0.07
     exagger
    0.07
     Sesso
    0.07
     underst
    0.07
    >Returns
    0.06
    üzel
    0.06
    strand
    0.06
    onen
    0.06
    Activations Density 0.004%

    No Known Activations